mlsanityData to 7 Oct 2026

Spell my name: keyword boosted speech recognition

arXiv 2110.02791 ↗First posted 6 Oct 2021cs.SD cs.CL eess.AScited by 10

Not on the map. Why?

Abstract (arXiv)

Recognition of uncommon words such as names and technical terminology is important to understanding conversations in context. However, the ability to recognise such words remains a challenge in modern automatic speech recognition (ASR) systems. In this paper, we propose a simple but powerful ASR decoding method that can better recognise these uncommon keywords, which in turn enables better readability of the results. The method boosts the probabilities of given keywords in a beam search based on acoustic model predictions. The method does not require any training in advance. We demonstrate the effectiveness of our method on the LibriSpeeech test sets and also internal data of real-world conversations. Our method significantly boosts keyword accuracy on the test sets, while maintaining the accuracy of the other words, and as well as providing significant qualitative improvements. This method is applicable to other tasks such as machine translation, or wherever unseen and difficult keywords need to be recognised in beam search.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 16 of its 27 references that are in the map. First posted on arXiv 6 Oct 2021.

Builds on

16 of 27 references.

References · 16

  1. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  2. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  3. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  4. 2017Regularizing and Optimizing LSTM Language Modelscited by 205
  5. 2020Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognitioncited by 185
  6. 2015On Using Monolingual Corpora in Neural Machine Translationcited by 149
  7. 2018Deep context: end-to-end contextual speech recognitioncited by 136
  8. 2021Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusioncited by 100
  9. 2020ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Contextcited by 96
  10. 2020Contextual RNN-T For Open Domain ASRcited by 85
  11. 2021SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Networkcited by 83
  12. 2020Deep Shallow Fusion for RNN-T Personalizationcited by 64
4 more
  1. 2018Simple Fusion: Return of the Language Modelcited by 30
  2. 2018Contextual Speech Recognition with Difficult Negative Training Examplescited by 28
  3. 2018End-to-end Speech Recognition with Word-based RNN Language Modelscited by 23
  4. 2020Fast and Robust Unsupervised Contextual Biasing for Speech Recognitioncited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 5; 2025: 3; 2026: 1.

10 papers.

  1. 2024Fast Context-Biasing for CTC and Transducer ASR models with CTC-based Word Spottercited by 7
  2. 2025NGPU-LM: GPU-Accelerated N-Gram Language Model for Context-Biasing in Greedy ASR Decodingcited by 7
  3. 2024InterBiasing: Boost Unseen Word Recognition through Biasing Intermediate Predictionscited by 5
  4. 2025TurboBias: Universal ASR Context-Biasing powered by GPU-accelerated Phrase-Boosting Treecited by 4
  5. 2025WCTC-Biasing: Retraining-free Contextual Biasing ASR with Wildcard CTC-based Keyword Spotting and Inter-layer Biasingcited by 3
  6. 2024Deep CLAS: Deep Contextual Listen, Attend and Spellcited by 2
  7. 2024Fast Streaming Transducer ASR Prototyping via Knowledge Distillation with Whispercited by 1
  8. 2024Unifying Global and Near-Context Biasing in a Single Trie Passcited by 1
  9. 2023N-gram Boosting: Improving Contextual Biasing with Normalized N-gram Targetscited by 0
  10. 2026TurboBias 2.0: Streaming Context-Biasing for Production-Efficient ASR Systemscited by 0